Systems and methods for determining patient hospitalization risk and treating patients

Abstract

A system and method for determining patient hospitalization risk and treating patients is disclosed. The system and method may include extracting patient data from one or databases corresponding to a pool of patients having end stage renal disease; using a predictive model with the extracted patient data to generate, for each of the patients, a respective expected probability for hospitalization within a predetermined time period; identifying a subset of patients having respective expected probabilities that are higher than other patients in the pool of patients; identifying, for each patient, at least one factor from the patient data that increased the expected probability of hospitalization; and based on the identified factors, determining and executing clinical interventions to lower the probability of hospitalization within the subset of the pool of patients.

1 . A method comprising:
 extracting patient data from one or databases corresponding to a pool of patients having end stage renal disease (ESRD);   using a predictive model with the extracted patient data to generate, for each of the patients in the pool of patients, a respective expected probability for hospitalization within a predetermined time period;   identifying a subset of the pool of patients having respective expected probabilities that are higher than other patients in the pool of patients;   identifying, for each patient of the subset of the pool of patients, at least one factor from the patient data that increased the expected probability of hospitalization; and   based on the identified factors, determining and executing clinical interventions to lower the probability of hospitalization within the subset of the pool of patients, wherein the clinical interventions include at least one of (a) administering one or more dialysis treatments in addition to a patient's existing dialysis schedule, (b) extending a patient's dialysis treatment time, (c) adjusting a patient's target weight for a dialysis treatment, (d) adjusting a dialysate sodium concentration for a patient's dialysis treatment, and (e) adjusting a patient's blood pressure medication.   
     
     
         2 . The method of  claim 1 , wherein the predictive model includes a gradient-boosting framework. 
     
     
         3 . The method of  claim 1 , wherein the at least one factor for each patient is identified using Shapley additive explanations. 
     
     
         4 . The method of  claim 1 , wherein the predetermined time period is 7 days or less. 
     
     
         5 . The method of  claim 1 , wherein the extracted patient data includes a patient's demographics, a patient's laboratory values, a patient's treatment data, or a patient's comprehensive assessment, or combinations thereof. 
     
     
         6 . The method of  claim 5 , wherein the patient's demographics includes the patient's date of birth, the patient's date of first dialysis, the patient's gender, the patient's race, the patient's ethnicity, or the patient's marital status, or combinations thereof. 
     
     
         7 . The method of  claim 5 , wherein the patient's laboratory values include a patient's hemoglobin levels, or a patient's albumin level, or combinations thereof. 
     
     
         8 . The method of  claim 5 , wherein the patient's laboratory values are provided as an average over a specified time period, a maximum value, a minimum value, a value spike, a value dip, or trending values, or combinations thereof. 
     
     
         9 . The method of  claim 5 , wherein a patient's treatment data includes a patient's vitals, and wherein the patient's vitals are provided as an average over a specified time period, a maximum value, a minimum value, a value spike, a value dip, or trending valves, or combinations thereof. 
     
     
         10 . The method of  claim 5 , wherein the patient's comprehensive assessment includes a patient's recent hospitalization history, a history of a patient's missed appointments, any patient's notes or complaints, a nurse's or other medical professional assessments, or any delivered medications, or combinations thereof. 
     
     
         11 . The method of  claim 1 , wherein the predictive model is built from historical data from other patients. 
     
     
         12 . The method of  claim 1 , further comprising generating a report that ranks the pool of patients according to their respective expected probabilities of hospitalization, wherein the report also provides the identified factors for each respective patient. 
     
     
         13 . The method of  claim 12 , further comprising providing the generated report to one or more health care providers. 
     
     
         14 . The method of  claim 1 , further comprising transmitting an automated alert to one or more health care providers, based on the expected probabilities of hospitalization. 
     
     
         15 . The method of  claim 1 , wherein the pool of patients are patients of an ESRD Seamless Care Organization (ESCO). 
     
     
         16 . A system for determining a risk of hospitalization for patients having end stage renal disease (ESRD), the system comprising:
 an integrated care system configured to:   extract patient data from one or databases corresponding to a pool of patients having end stage renal disease (ESRD);   use a predictive model with the extracted patient data to generate, for each of the patients in the pool of patients, a respective expected probability for hospitalization within a predetermined time period;   identify a subset of the pool of patients having respective expected probabilities that are higher than other patients in the pool of patients;   identify for each patient of the subset of the pool of patients, at least one factor from the patient data that increased the expected probability of hospitalization; and   generate a report that ranks the pool of patients according to their respective expected probabilities of hospitalization, wherein the report also provides the identified factors for each respective patient.   
     
     
         17 . The system of  claim 16 , wherein the predictive model includes a gradient-boosting framework. 
     
     
         18 . The system of  claim 16 , wherein the integrated care system is configured to identify the at least one factor for each patient using Shapley additive explanations. 
     
     
         19 . The system of  claim 16 , wherein the predetermined time period is 7 days or less. 
     
     
         20 . The system of  claim 16 , wherein the extracted patient data includes a patient's demographics, a patient's laboratory values, a patient's treatment data, or a patient's comprehensive assessment, or combinations thereof. 
     
     
         21 . The system of  claim 20 , wherein the patient's demographics includes the patient's date of birth, the patient's date of first dialysis, the patient's gender, the patient's race, the patient's ethnicity, or the patient's marital status, or combinations thereof. 
     
     
         22 . The system of  claim 20 , wherein the patient's laboratory values include a patient's hemoglobin levels, or a patient's albumin level, or combinations thereof. 
     
     
         23 . The system of  claim 20 , wherein the patient's laboratory values are provided as an average over a specified time period, a maximum value, a minimum value, a value spike, a value dip, or trending values, or combinations thereof. 
     
     
         24 . The system of  claim 20 , wherein a patient's treatment data includes a patient's vitals, and wherein the patient's vitals are provided as an average over a specified time period, a maximum value, a minimum value, a value spike, a value dip, or trending valves, or combinations thereof. 
     
     
         25 . The system of  claim 20 , wherein the patient's comprehensive assessment includes a patient's recent hospitalization history, a history of a patient's missed appointments, any patient's notes or complaints, a nurse's or other medical professional assessments, or any delivered medications, or combinations thereof. 
     
     
         26 . The system of  claim 16 , wherein the predictive model is built from historical data from other patients.